© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93823
    Prev
    Next
    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"";
    -0.50
    pson
    -0.45
     abund
    -0.41
    CppCodeGen
    -0.41
    band
    -0.41
    ménage
    -0.41
    ydı
    -0.41
     יד
    -0.41
    pId
    -0.41
     band
    -0.40
    POSITIVE LOGITS
    StoryboardSegue
    0.81
    новниш
    0.76
     صوتيه
    0.71
    findpost
    0.68
     initComponents
    0.64
    脚注の使い方
    0.63
    IsMutable
    0.63
    AnchorStyles
    0.63
    enumi
    0.61
    providedIn
    0.61
    Activations Density 0.001%

    No Known Activations